mlsanityData to 7 Oct 2026

Lexically Constrained Neural Machine Translation with Levenshtein Transformer

arXiv 2004.12681 ↗First posted 27 Apr 2020cs.CLcited by 45

Not on the map. Why?

Abstract (arXiv)

This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search decoding with significantly higher computational overheads. Leveraging the flexibility and speed of a recently proposed Levenshtein Transformer model (Gu et al., 2019), our method injects terminology constraints at inference time without any impact on decoding speed. Our method does not require any modification to the training procedure and can be easily applied at runtime with custom dictionaries. Experiments on English-German WMT datasets show that our approach improves an unconstrained baseline and previous approaches.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 14; 2023: 16; 2024: 1; 2025: 3.

45 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2023AR-Diffusion: Auto-Regressive Diffusion Model for Text Generationcited by 113
  3. 2023Amortizing intractable inference in large language modelscited by 94
  4. 2022Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoisecited by 79
  5. 2023Tractable Control for Autoregressive Language Generationcited by 65
  6. 2022Controllable Text Generation with Neurally-Decomposed Oraclecited by 41
  7. 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretrainingcited by 25
  8. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  9. 2021Sketch and Refine: Towards Faithful and Informative Table-to-Text Generationcited by 21
  10. 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraintscited by 21
  11. 2021Facilitating Terminology Translation with Target Lemma Annotationscited by 19
  12. 2023Songs Across Borders: Singable and Controllable Neural Lyric Translationcited by 11
33 more
  1. 2021Encouraging Neural Machine Translation to Satisfy Terminology Constraintscited by 10
  2. 2022Integrating Vectorized Lexical Constraints for Neural Machine Translationcited by 9
  3. 2021WeTS: A Benchmark for Translation Suggestioncited by 8
  4. 2023User Adaptive Language Learning Chatbots with a Curriculumcited by 8
  5. 2021GWLAN: General Word-Level AutocompletioN for Computer-Aided Translationcited by 7
  6. 2022Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Promptscited by 7
  7. 2023Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translationcited by 7
  8. 2023Toward Unified Controllable Text Generation via Regular Expression Instructioncited by 7
  9. 2022Integrating Translation Memories into Non-Autoregressive Machine Translationcited by 5
  10. 2021Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021cited by 4
  11. 2022DICTDIS: Dictionary Constrained Disambiguation for Improved NMTcited by 4
  12. 2021Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Predictioncited by 3
  13. 2021Rule-based Morphological Inflection Improves Neural Terminology Translationcited by 3
  14. 2022Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraintscited by 3
  15. 2022Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Reviewcited by 3
  16. 2023Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraintscited by 3
  17. 2024SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervisioncited by 3
  18. 2021InFillmore: Frame-Guided Language Generation with Bidirectional Contextcited by 2
  19. 2021Lingua Custodia's participation at the WMT 2021 Machine Translation using Terminologies shared taskcited by 2
  20. 2022Bilingual Synchronization: Restoring Translational Relationships with Editing Operationscited by 2
  21. 2023Towards Example-Based NMT with Multi-Levenshtein Transformerscited by 2
  22. 2022Accurate Online Posterior Alignments for Principled Lexically-Constrained Decodingcited by 1
  23. 2023Disambiguated Lexically Constrained Neural Machine Translationcited by 1
  24. 2023Joint Learning of Wording and Formatting for Singable Melody-to-Lyric Generationcited by 1
  25. 2025(G)I-DLE: Generative Inference via Distribution-preserving Logit Exclusion with KL Divergence Minimization for Constrained Decodingcited by 1
  26. 2025It Takes Two: A Dual Stage Approach for Terminology-Aware Translationcited by 1
  27. 2022A Template-based Method for Constrained Neural Machine Translationcited by 0
  28. 2022Findings of the WMT 2022 Shared Task on Translation Suggestioncited by 0
  29. 2023Unified Model Learning for Various Neural Machine Translationcited by 0
  30. 2023A Benchmark for Text Expansion: Datasets, Metrics, and Baselinescited by 0
  31. 2023IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systemscited by 0
  32. 2023Improving Neural Machine Translation by Multi-Knowledge Integration with Promptingcited by 0
  33. 2025Lingua Custodi's participation at the WMT 2025 Terminology shared taskcited by 0